학교 LMS 읽기

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint/openWorldHint/destructiveHint, and the description adds substantial context beyond them: the download side effect of saving a file to the materials folder, the credential model (token or calendar URL, never a password), the reduced capability of calendar-only connections, and a prompt-injection warning that LMS text is third-party data. That last point is a real behavioral safeguard an agent could not infer from the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core purpose, then scoped per action in short lines, ending with the error path and an example. Every line carries information, though the clipped phrasing ('Calendar URL only (no token): deadlines only') is slightly terse and could be clearer at the cost of a few words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, but the description names the data domains returned (courses, deadlines, announcements, file listings) and explains the download artifact and its handoff to read_document. Setup prerequisites, error handling, and injection safety are all covered; only exact return fields and pagination remain unspecified, which is acceptable for a read-only aggregator.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 75% and already documents days (1-120), item and course, so the baseline is already high; the description still adds meaning by tying each parameter to specific actions (download needs course + item, course is an id or name fragment, schools uses the school name). The worked example JSON reinforces the action/days pairing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Opens with a specific verb and resource: read-only access to the user's school LMS, naming the platforms (Canvas/LearningX, Moodle/Coursemos) and the four data types (courses, deadlines, announcements, files). It also states what the tool will never do ('Never submits or posts'), which separates it from any write-capable sibling and from read_document, which it hands downloaded files to.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives per-action guidance: 'schools' works without setup, calendar-URL-only connections yield deadlines only, download requires course + item from action='files'. It also covers the failure path, telling the agent to relay setup steps and never ask for a password. The only gap is that it doesn't explicitly state when to prefer a sibling over this tool beyond the implicit read_document handoff.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.